End of training

README.md

@@ -3,11 +3,15 @@ library_name: transformers
 license: llama3
 base_model: meta-llama/Meta-Llama-3-8B
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- llama-duo/synth_classification_dataset_dedup
 model-index:
 - name: llama3.1-8b-gpt4o_100k_classification-fft
   results: []
@@ -18,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3.1-8b-gpt4o_100k_classification-fft
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the generator dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the llama-duo/synth_classification_dataset_dedup dataset.
 It achieves the following results on the evaluation set:
 - Loss: 2.2658
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 2.265784978866577,
+    "eval_runtime": 2.1012,
+    "eval_samples": 16,
+    "eval_samples_per_second": 0.952,
+    "eval_steps_per_second": 0.476,
     "total_flos": 12379572142080.0,
     "train_loss": 1.644804019968218,
     "train_runtime": 4500.3652,

config.json

@@ -26,6 +26,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.45.1",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 128258
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 2.265784978866577,
+    "eval_runtime": 2.1012,
+    "eval_samples": 16,
+    "eval_samples_per_second": 0.952,
+    "eval_steps_per_second": 0.476
+}

runs/Sep28_00-11-17_637888cb4368/events.out.tfevents.1727488044.637888cb4368.91844.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd23b4a15e1bb4240f3b9be146727ba4ed93543a2ba0ee7d069c6dd519ab8422
+size 359